First steps in the course Practical Deep Learning for Coders

You cannot be a part of the conversation if you do not start somewhere, so this is my starting point at machine learning. I wanted to start with Hugging Face , an open source platform for machine learning. They offer tutorials and advice, but I am not currently at that level, so I am following their first recommended course Practical Deep Learning for Coders . The course was recorded at The University of Queensland and covers models, NLP, tabular analysis, deploying models, etc over 25 lessons. It also include the book, Deep Learning for Coders with fastai & PyTorch. 

The first step is signing up for Kaggle a place to learn data science and to build a portfolio, as well as downloading JuypterLab a web-based interactive development environment for notebooks, code, and data.

While JuypterLabs downloads it's probably best to start reading because it's taking me awhile. The book starts with a history of neural networks, starting in 1943. Walter Pitts a self taught logician and Warren McCulloch were able to make a model for a neuron using logical calculus. Then delves into how to learn deep learning.

After reading for awhile I dropped the idea of using brew to install jupyterlab and used pip to install the classic Jupyter Notebook, since that is the one I have played around with in the past.

This course looks incredibly interesting even though I have barely scratched the service of the first chapter. I am going to keep applying myself to it, and see where it goes.